Open Source Image De-Noising 205
GREYCstoration is an open-source tool able to de-noise, inpaint, or resize 2D color images. This is a command-line program developed by the IMAGE team of the GREYC Lab in France and is available for Unix, Mac, and Windows systems under the CeCILL license. The algorithm is based on anisotropic diffusion partial differential equations. These equations are able to smooth an image while preserving its main structures. The demo page presents interesting examples of color image de-noising and reconstruction. This is a serious free alternative to commercial products like Noise Ninja or Neat Image that perform the same kinds of operations. The tool is still a little bit hard to use (command-line based), but I hope the simple C++ API will ease the integration of the algorithm in more user-friendly interfaces. Previous versions of GREYCstoration are already available in Digikam and Krita.
Re:Color me impressed! (Score:4, Insightful)
I disagree. They are overly smoothed and detail is destroyed. They look like the type of thing a noob makes upon discovering video filters. For example, look at the delicate features in the jellyfish or the pig's hair. This samples look more like demonstrations of soften or posterization filters. They should also use real, not artificial, noise.
Re:Does it work on 12 or 16 bits/channel images? (Score:2, Insightful)
With that, how about GIMP gets USABLE before ya cram in more "features".
Re:No more ISO 80? (Score:2, Insightful)
Yeah, looking at the demo pictures I see this is basically replacing noise with blur.
I was thinking about this recently, and I think what we need is a digital camera which can somehow take multiple short exposure shots one after the other and then combine them into a single photo. The algorithm would have to be smart enough to detect movement of both the camera and the scenery in-between frames, so we're talking advanced software, but it does seem possible.
Otherwise, having to choose between underexposed, noisy, and blurry, when shooting telephoto in anything but the brightest of sunlight just doesn't seem right... I guess I could just carry a tripod with me everywhere :)
Re:The real question is... (Score:4, Insightful)
Usually in wars people on both sides have weapons. Otherwise the war doesn't last very long.
Anti-CAPTCHA tools only help the Blind (Score:3, Insightful)
Re:Picture Cooler (Score:3, Insightful)
FREE Picture Cooler--Noise reduction and most other adjustements 2.45 -- last update 5 JAN 2007
Temporaly 15$ for the Full version
Related software (Score:3, Insightful)
Re:Color me impressed! (Score:3, Insightful)
Re:Anisotropic diffusion (Score:3, Insightful)
Re:Oh yeah, baby. You the PRO! (Score:5, Insightful)
Being a research scientist doesn't necessarily qualify someone as having a photographer's eye. Nobody's saying the guy couldn't research circles around any of us. What the parent poster said is his de-noise filter is way too aggressive and obscures image detail. That appears to be true, at least judging by the settings he's using for his demo shots.
Sufficiently advanced noise is indistinguishable from the stuff that comes out of a cheap imaging device
Not really true, because the noise that comes out of any imaging device (cheap or otherwise) is not random. It fits a particular profile that's unique to that model of device, or even that particular unit. Advanced photo filtering algorithms (including those used in the in-camera processors that convert raw image data to jpg image files) use that individual profile to filter noise. They're not trying to figure out what's noise and what isn't on the fly, which is at best an imperfect science, and that's being charitable. They have a good idea before they even look at an image what the noise is going to look like, so they do a better job of removing it without sacrificing detail.
The more advanced filters like NeatImage are also almost infinitely configurable in what noise they go after and where, and how aggressive they are. Now, this guy's algorithm seems to be pretty configurable as well, so maybe he just didn't use very good settings himself on most of his image demos, and the algorithm is actually capable of better results. He does seem like he's a better scientist than image-maker so that's entirely possible.
It would be interesting to see what could be done with this if it was given an intuitive GUI and put in the hands of some real photographers. (Yes, even real photographers have to shoot at ISO 800 and above occasionally, and would benefit from noise reduction that actually works without sacrificing detail.)
Re:He did use real noise. (Score:3, Insightful)
Look at the top of the ridge in the inner ear and the wrinkles in the fabric. The near-blacks also look like they've been darkened a bit and flattened (lines between the baby's fingers.) It's still a little too posterized. With natural subjects there's a point at which it's very hard to remove noise without destroying detail. These samples are all overly smoothed. They're not horrible, they're just done too harshly. A lot of the time this happens because the process assumes the original source is pure RGB. The vast majority of digital source isn't. It's interpolated color and needs to be treated as such.
Re:Does it work on 12 or 16 bits/channel images? (Score:2, Insightful)
Only in the same way that having a small heap of books on the floor is just a particular form of a bookcase.
Seriously, I dunno why he got modded flamebait, but the GIMP interface _is_ horrible and every non-geek I've tried to convert to GIMP found it horrible. It's not even just the heap of disconnected windows. Just about everything in it works non-intuitively, or in some own way that breaks any reflexes and expectations you might already have.
As a quick example, look at the stupid image mode menu. Yeah, the one with RGB, grayscale and indexed options. Just about any other Windows program would use a checkmark next to the active mode, but nah, the Gimp grays it out, which normally means a disabled or non-available option. It's not just sending the wrong message to anyone used to the normal use of those visual cues, it actually manages to be less useful by making one visual cue mean two fundamentally different things. Disabled is very different from "it's already selected": disabled can mean (and is usually used to mean) something that just isn't possible in that particular situation. E.g., if for some reason that particular image simply can't be indexed. Already selected or already active, on the other hand, is pretty much the opposite: it's very much possible, and in fact it's what's currently happening.
Honestly, as it is, the Gimp just makes the case of why someone would prefer to pay money for a usable product, instead of going with the crap but free (as in either beer or freedom or whatever you wish) equivalent. It just makes a (false) "you get what you pay for" point, that then gets used against other free products. Normal people don't fight ideological crusades, they just want something that works and is easy to use, so "but the Gimp is GPLed" points are lost on them. And even "free as in beer" points tend to get lost when the freely downloadable version has a crap interface. At some point they'd rather pay some money and get a usable product instead. It's, if you will, as in buying a car vs the "free as in beer" walking to work. Most people will get a car.
Re:Oh yeah, baby. You the PRO! (Score:3, Insightful)